Commits · c68b5c63eba0ecccda8ab34ca1829cb4ced2c430 · OpenDAS / vllm_cscc · GitLab

28 May, 2025 19 commits
- [Misc] fix olmoe model layer can't laod in tp gt 1 (#18828) · c68b5c63
  rongfu.leng authored May 29, 2025
```
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
```
  c68b5c63
- [Core] Add Lora Support to Beam Search (#18346) · 321331b8
  Alex Brooks authored May 28, 2025
```
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
```
  321331b8
- decrement server_load on listen for disconnect (#18784) · 6e4cea1c
  daniel-salib authored May 28, 2025
```
Signed-off-by: Daniel Salib <danielsalib@meta.com>
```
  6e4cea1c
- [Frontend] add run batch to CLI (#18804) · 435fa954
  Reid authored May 28, 2025
```
Signed-off-by: reidliu41 <reid201711@gmail.com>
Co-authored-by: reidliu41 <reid201711@gmail.com>
```
  435fa954
- Enable Pydantic mypy checks and convert configs to Pydantic dataclasses (#17599) · 4c2b38ce
  Harry Mellor authored May 28, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  4c2b38ce
- [Platform][Dist] Make torch distributed process group extendable (#18763) · d781930f
  Mengqing Cao authored May 28, 2025
```
Signed-off-by: Mengqing Cao <cmq0113@163.com>
```
  d781930f
- [BugFix] FA2 MLA Accuracy Issue (#18807) · ce75efee
  Lucas Wilkinson authored May 28, 2025
```
Signed-off-by: LucasWilkinson <lwilkinson@neuralmagic.com>
```
  ce75efee
- Fix PiecewiseCompileInterpreter (#17338) · aa42561e
  Richard Zou authored May 28, 2025
```
Signed-off-by: rzou <zou3519@gmail.com>
```
  aa42561e
- [CI] improve embed testing (#18747) · de65fc8e
  wang.yuqi authored May 28, 2025
  
  de65fc8e
- [Deprecation] Remove fallbacks for Embeddings API (#18795) · 0c492b78
  Cyrus Leung authored May 28, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  0c492b78
- [Deprecation] Remove unused sync methods in `async_timeout` (#18792) · 0f0926b4
  Cyrus Leung authored May 28, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  0f0926b4
- [Deprecation] Require overriding `get_dummy_text` and `get_dummy_mm_data` (#18796) · 7f2c1a87
  Cyrus Leung authored May 28, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  7f2c1a87
- [V1] [Bugfix] eagle bugfix and enable correct lm_head for multimodal (2) (#18781) · 5e13c07d
  RonaldBXu authored May 27, 2025
```
Signed-off-by: Ronald Xu <ronaldxu@amazon.com>
```
  5e13c07d
- [V1] fix torch profiling for V1 offline scenarios (#18445) · 774c5fde
  Divakar Verma authored May 27, 2025
```
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
```
  774c5fde
- [Bugfix]: correctly propagate errors message caught at the chat_templating... · 9a21e331
  Guillaume Calmettes authored May 28, 2025
```
[Bugfix]: correctly propagate errors message caught at the chat_templating step to the client (#18769)
Signed-off-by: Guillaume Calmettes <gcalmettes@scaleway.com>
```
  9a21e331
- [Bugfix] Fix nomic max_model_len (#18755) · 3e9ce609
  wang.yuqi authored May 28, 2025
  
  3e9ce609
- [rocm] Fix wrong attention log (#18764) · 794ae1f5
  fxmarty-amd authored May 28, 2025
```
Signed-off-by: Felix Marty <felmarty@amd.com>
```
  794ae1f5
- [Core] Improve Tensor serialisation (#18774) · d73a9457
  Lukas Geiger authored May 28, 2025
```
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
```
  d73a9457
- [Bugfix] Disable prefix caching by default for benchmark (#18771) · 51e98e4f
  cascade authored May 27, 2025
```
Signed-off-by: cascade812 <cascade812@outlook.com>
```
  51e98e4f
27 May, 2025 16 commits
- Support datasets in `vllm bench serve` and sync with benchmark_[serving,datasets].py (#18566) · e56f44d9
  Michael Goin authored May 27, 2025
  
  e56f44d9
- [Neuron] Support quantization on neuron (#18283) · e0cbad4e
  Satyajith Chilappagari authored May 27, 2025
```
Signed-off-by: Satyajith Chilappagari <satchill@amazon.com>
```
  e0cbad4e
- [Bugfix] Mistral tool calling when content is list (#18729) · 58738772
  Michael Goin authored May 27, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  58738772
- [Core] Automatically cast multi-modal input dtype (#18756) · 696259ca
  Cyrus Leung authored May 27, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  696259ca
- optimize get_kv_cache_torch_dtype (#18531) · 6b6d4961
  chunxiaozheng authored May 27, 2025
```
Signed-off-by: idellzheng <idellzheng@tencent.com>
```
  6b6d4961
- Disable prefix cache by default for benchmark (#18639) · aaa4ac1c
  cascade authored May 27, 2025
```
Signed-off-by: cascade812 <cascade812@outlook.com>
```
  aaa4ac1c
- [V1][Metrics] Add API for accessing in-memory Prometheus metrics (#17010) · 06a03380
  Mark McLoughlin authored May 27, 2025
```
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
```
  06a03380
- [CI/Build] Remove imports of built-in `re` (#18750) · 4318c055
  Cyrus Leung authored May 27, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  4318c055
- [Doc] Convert Sphinx directives ( `{class}`, `{meth}`, `{attr}`, ...) to... · a68e293c
  Hyogeun Oh (오효근) authored May 27, 2025
```
[Doc]  Convert Sphinx directives ( `{class}`, `{meth}`, `{attr}`, ...) to MkDocs format for better documentation linking (#18663)
Signed-off-by: Zerohertz <ohg3417@gmail.com>
```
  a68e293c
- [BUG FIX] minicpm (#18739) · 68811079
  Shawn Huang authored May 27, 2025
```
Signed-off-by: huangyuxiang03 <huangyx0321@gmail.com>
Co-authored-by: huangyuxiang03 <huangyx0321@gmail.com>
```
  68811079
- Minor fix about MooncakeStoreConnector (#18721) · c24b1572
  maobaolong authored May 27, 2025
```
Signed-off-by: baoloongmao <baoloongmao@tencent.com>
```
  c24b1572
- feat(rocm-support): support mamba2 on rocm (#18565) · a547aeb8
  almersawi authored May 27, 2025
```
Signed-off-by: Islam Almersawi <islam.almersawi@openinnovation.ai>
Co-authored-by: Islam Almersawi <islam.almersawi@openinnovation.ai>
```
  a547aeb8
- [FEAT] [ROCm] Upgrade AITER Fused MoE kernels. (#18271) · d260f799
  vllmellm authored May 27, 2025
```
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
```
  d260f799
- [Model][Gemma3] Cast image pixel values already on CPU (#18732) · b50602d5
  Lukas Geiger authored May 27, 2025
```
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
```
  b50602d5
- [V1][Quantization] Add CUDA graph compatible v1 GGUF support (#18646) · 1f1b1bc0
  Isotr0py authored May 27, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  1f1b1bc0
- [Model][Gemma3] Simplify image input validation (#18710) · 0eebd748
  Lukas Geiger authored May 27, 2025
```
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
```
  0eebd748
26 May, 2025 5 commits
- [V1][Sampler] Improve performance of FlashInfer sampling by sampling logits... · e7523c2e
  Lukas Geiger authored May 26, 2025
```
[V1][Sampler] Improve performance of FlashInfer sampling by sampling logits instead of probs (#18608)
```
  e7523c2e
- [Bugfix] Fix Llama GGUF initialization (#18717) · a869baca
  Cyrus Leung authored May 26, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  a869baca
- [Doc] Move examples and further reorganize user guide (#18666) · 82e2339b
  Cyrus Leung authored May 26, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  82e2339b
- [Model] Add support for YARN in NemotronNAS models (#18427) · 6d68030f
  Naveassaf authored May 26, 2025
```
Signed-off-by: Nave Assaf <nassaf@nvidia.com>
```
  6d68030f
- [CI] fix dump_input for str type (#18697) · 5a2c76cb
  Ning Xie authored May 26, 2025
```
Signed-off-by: Andy Xie <andy.xning@gmail.com>
```
  5a2c76cb